BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.hku.hk
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20250120T110000
DTEND;TZID=Asia/Hong_Kong:20250120T120000
DTSTAMP:20260510T132832
CREATED:20250116T025553Z
LAST-MODIFIED:20250211T042315Z
UID:108129-1737370800-1737374400@ece.hku.hk
SUMMARY:Edges Empowering AI\, Embracing LLMs: Issues\, Technologies\, and Applications
DESCRIPTION:Abstract\nAccelerated by the rapid advancements in AI and IoT technologies\, there is an urgent need to extend AI capabilities to the network edge to fully harness the potential of big data. To address this demand\, edge Intelligence has emerged as a promising paradigm for enabling distributed\, computation-intensive AI applications on edge devices. This talk explores the key dimensions of edge intelligence: data\, models\, and systems. It involves data evaluation by analyzing its contribution to model performance and investigates strategies for optimizing edge models in dynamic edge environments. Special attention is given to technologies such as distributed training (federated edge learning as an example)\, inference acceleration\, and model compression tailored for edge deployments. Furthermore\, with the advent of large language models (LLMs) and their overwhelming computational requirements\, the talk examines the evolving role of edge intelligence. Some open questions remain: e.g.\, how edge systems can integrate with and complement these foundational models\, addressing challenges such as resource constraints and latency while exploring potential synergies in hybrid edge-cloud architectures. \nSpeaker\nProf. Yinglei Teng\nProfessor\,\nBeijing University of Posts and Telecommunications \nBiography of the Speaker\nYinglei Teng\, a professor at Beijing University of Posts and Telecommunications\, specializes in wireless communications\, stochastic optimization and edge intelligence. She received funding from renowned programs\, including the NSFC\, National Key R&D Young Scientist Project\, Huawei\, China Mobile\, etc. She authored over 30 high-quality SCI papers\, holds more than 80 invention patents\, and contributed to 8 industry standards. She was recognized with honors such as the China Association for Science and Technology Special Award and the Beijing Science and Technology Award. Her recent research focuses on edge intelligence\, ML/AI for PHY\, and millimeter-wave technologies\, etc. \nOrganisers\nProf. Kaibin Huang & Prof. Xianhao Chen\nDepartment of Electrical and Electronic Engineering\,\nThe University of Hong Kong \nAll are welcome! 
URL:https://ece.hku.hk/events/20250120-1/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Highlights,Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2025/01/1280-4.jpg
END:VEVENT
END:VCALENDAR